README.md

metadata

license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-ro
tags:
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: opus-mt-en-ro-finetuned-en-to-ro
    results: []

opus-mt-en-ro-finetuned-en-to-ro

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-ro on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.2886
• Bleu: 28.2215
• Gen Len: 34.1036

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
0.7413	1.0	38145	1.2886	28.2215	34.1036

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1